Achieving high availability for modern software requires fast and correct recovery from inevitable faults. This is notoriously difficult. Existing techniques either guarantee correctness by discarding all state but suffer from long downtime, or preserve all state to recover quickly but reintroduce the fault.

We present BORA (Bag Optimizer for Robotic Analysis), a file system middleware that optimizes the acquisition of bags, which are specially formatted files used to store timestamped ROS (robot operating system) messages. BORA sits between ROS and an existing file system to conduct semantic-aware data pre-processing. In particular, it categorizes ROS bag data into multiple groups with each having a distinct label. BORA predigests data index constructions and reduces file open time via a hash-based label management scheme. It is also capable of providing ROS analytic applications with only data needed without a sequence of data searching and locating operations. We implement a BORA prototype, which is then integrated into three computing platforms: a single-node server, a four-node PVFS storage cluster, and a Tianhe-1A Supercomputer storage subsystem. Next, we evaluate the BORA prototype on the three platforms using four real-world ROS applications. Our experimental results show that compared to a traditional bag management scheme BORA improves data acquisition performance by up to 11x. In addition, it offers up to 10x data acquisition performance improvement and 3,100x bags open improvement under a swarm robotics data analysis scenario where data is retrieved across multiple bags simultaneously.